The value of artificial intelligence and machine learning applications for use in heritage research is increasingly appreciated [1]. In specific areas, notably remote sensing, data sets have increased in extent and resolution to the point that manual interpretation is problematic and availability of skilled interpreters to undertake such work is limited. Interpretation of geophysical data sets associated with prehistoric submerged landscapes is particularly challenging. Following the last glacial, sea levels rose 120 metres globally, and vast, habitable landscapes were lost to the sea. These landscapes were inaccessible until extensive remote sensing data sets were provided by the offshore energy sector. In this paper, we provide results of a research programme centred on AI applications using data from the southern North Sea. Here, an area of c.188,000 km2 of habitable terrestrial land was inundated between c. 20,000 BP and 7,0000 BP, along with the cultural heritage it contained [2]. As part of this project, machine learning tools were applied to detect and interpret features of archaeological significance from shallow seismic data. The output provides a proof-of-concept model demonstrating verifiable results and the potential for further, more complex leveraging of AI interpretation for the study of submarine palaeolandscapes. Image: Adobe Firefly Generative AI using keywords - marsh landscape deep underwater, auroch skull half-buried in peat

Weeds are unwanted and invasive plants that proliferate and compete for resources such as space, water, nutrients, and sunlight, affecting the quality and productivity of the desired crops. Weed detection is crucial for the application of precision agriculture methods and for this purpose machine learning techniques can be used, specifically convolutional neural networks (CNN). This study focuses on the search for CNN architectures and technology used to detect and identify weeds in different crops; 61 articles applying CNN architectures and technology were analyzed in the last five years (2019-2023). The results show the used of different devices to acquire the image for training, such as digital cameras, smartphones, and drone cameras. Additionally, the YOLO family and algorithms are the most widely adopted architectures, followed by VGG, ResNet, Faster R-CNN, AlexNet, and MobileNet, respectively. This study provides an update on CNNs that will serve as a starting point for researchers wishing to implement these weed detection and identification techniques.

Haze always shrouds satellite images, obscuring valuable geographic information for military surveillance, natural calamity surveillance and mineral resource exploration. Satellite image dehazing (SID) provides the possibility for better applications of satellite images. Most of the existing dehazing methods are tailored for natural images and are not very effective for satellite images with non-homogeneous haze since the semantic structure information and inconsistent attenuation are not fully considered. To tackle this problem, this study proposes a hierarchical semantic-guided contextual structure-aware network (SCSNet) for satellite image dehazing. Specifically, a hybrid CNN-transformer architecture integrated with a hierarchical semantic guidance (HSG) module is presented to learn semantic structure information by synergetically complementing local representation from non-local features. Furthermore, a cross-layer fusion (CLF) module is specially designed to replace the traditional skip connection during the feature decoding stage, so as to reinforce the attention to the spatial regions and feature channels with more serious attenuation. The results on the SateHaze1k, RS-Haze, and RSID datasets demonstrate that the proposed SCSNet can achieve effective dehazing and outperforms existing state-of-the-art methods.

Stock market prediction is a challenging task to perform, as we know the fluctuations that take place in the market makes it versatile and hard to predict the prices. In this research, we have explored the power of usage of hybrid ensemble algorithms to improve the predictive accuracy in the stock market forecasting. Our research comprises construction and evaluation of diverse hybrid models using different algorithms. The methodology presented in the paper involves comprehensive data preparation, feature engineering, and model normalization. Evaluating the different hybrid models, one stands out distinctly: LSTM (long short-term memory networks) + GRU (Gated recurrent units) + Conv1D (one-dimensional convolutional layer) hybrid. It illustrated its potential to revolutionize decision-making tools for investors and financial analysts in stock market analytics. The harmonious integration of algorithms not only underscores the effectiveness of hybrid modeling but also beckons for further exploration within the ever-evolving domain of predictive modeling, driven by the pursuit of precision and accuracy. This model shows a remarkable accuracy metrics including a Mean Absolute Error (MAE) of 0.95, a Mean Squared Error (MSE) of 2.1222, a Root Mean Squared Error (RMSE) of 1.52, and a R-squared (R2) score of 0.9982.

Hypoglossal nerve stimulator (HGNS) is a minimally invasive device used for treating obstructive sleep apnea (OSA). The conventional implantable HGNS is a device that consists of a stimuli generator, a breathing sensor, and electrodes connected to the hypoglossal nerve via leads. However, this implant is bulky and causes significant trauma. In this paper, we propose a minimally invasive HGNS based on an electrocardiogram (ECG) sensor and a wireless power transfer (WPT), consisting of a wearable breathing monitor and an implantable stimulator. The breathing external monitor utilizes an ECG sensor to identify abnormal breathing patterns associated with OSA with 88.68$\%$ accuracy, achieved through the utilization of a Convolutional Neural Network (CNN) algorithm. With a skin thickness of 5mm and a receiving coil diameter of 9mm, the power conversion efficiency was measured at 31.8$\%$. The implantable device, on the other hand, is composed of a front-end CMOS Power Management Module (PMM), a Binary Phase Shift Keying (BPSK)-based data demodulator, and a bipolar biphasic current stimuli generator. The PMM, with a silicon area of 0.06 $mm^2$ (excluding pads), demonstrates a power conversion efficiency of 77.5$\%$ when operating at a receiving frequency of 2 MHz. Furthermore, it offers three-voltage options (1.2V, 1.8V, and 3.1V). Within the data receiver component, a low-power BPSK demodulator has been ingeniously incorporated, consuming only 42 $\mu$W when supplied with a voltage of 0.7V. The performance is achieved through the implementation of the self-biased phase-locked loop (PLL) technique. The stimuli generator delivers biphasic constant currents, providing a 5-bit programmable range spanning from 0 to 2.4 mA. The functionality of proposed ECG and WPT-based HGNS was validated, representing a highly promising solution for the effective management of OSA, all while minimizing trauma and space requirements.

Social networks have captured the attention of many people worldwide. However, these services have also attracted a considerable number of malicious users whose purpose is to compromise digital assets of other members by using messages as an attack vector to execute different variants of cyberattacks against them. Therefore, this work presents an approach based on Natural Language Processing tools and a Convolutional Neural Network architecture to detect and classify, on social network messages, four types of cyberattacks, such as malware, phishing, spam, and even one whose purpose is deceiving the user into spreading malicious messages to other users, which in this work is identified as bot attacks. One notable feature of this work is that it analyzes textual content without depending on any characteristics from a specific social network, making its analysis independent from particular data sources. Finally, this work was tested on real data, demonstrating its results in two stages. The first detects the existence of any of the four cyberattacks within the message, obtaining an accuracy value of 0.91. After detecting a message as a cyberattack, the next stage is to classify it into one of the four types of cyberattack, achieving an accuracy value of 0.82.

Deep learning is improving by leaps and bounds in remote sensing images (RSIs) analysis, pre-trained convolutional neural networks (CNNs) have shown remarkable performance in remote sensing image scene classification (RSISC). Nonetheless, pre-trained CNNs require massive annotated data as samples for data training. When labeled samples are not sufficient, the most common solution is to the pre-trained CNNs using a great deal of natural image dataset (e.g. ImageNet). However, these pre-trained CNNs require a large quantity of labelled data for training, which is often not feasible in RSISC, especially when the target RSIs have different imaging mechanisms from RGB natural images. In this paper, we proposed an improved hybrid classical-quantum transfer learning CNNs composed of classical and quantum elements to classify open-source RSI dataset. The classical part of the model is made up of a ResNet network which extracts useful features from RSI datasets. To further refine the network performance, a tensor quantum circuit is subsequently employed by tuning parameters on near-term quantum processors. We tested our models on open-source RSI dataset. In our comparative study, we have concluded that the hybrid classical-quantum transferring CNN has achieved better performance than other pre-trained CNNs based RSISC methods with small training samples. Moreover, it has been proved that the proposed algorithm improves the classification accuracy while greatly decreasing sum of model parameters and sum of training data.

Accurately estimating a person's age is crucial for identity verification at all critical checkpoints, including airports, land borders, and seaports. Human gait may be used as a biometric identifier and indicator of age, among other things. This study aims to develop methods for estimating a person's age by observing their walk. In this paper, a novel technique for preprocessing the proposed gait dataset has been used by utilizing a combination of the gait energy image (GEI), the accumulated frame difference energy image (AFDEI), and the invariant moment of the image. The proposed technique outperformed state-of-the-art methods in terms of accuracy. The proposed method was tested and evaluated using a convolutional neural network (CNN), and it achieved an average accuracy of 90.35% across 14 different view angles within 5 K-Fold, the proposed method resulted in 94.68% and 94.54% in 30º and 75º view degree respectively. concluding that the approach is effective and promising for estimating age using human gait.

Industrial process control systems commonly exhibit features of time-varying, strong coupling, and strong nonlinearity. Obtaining accurate mathematical models of these nonlinear systems and achieving satisfactory control performance is still a challenging task. In this paper, data-driven modeling techniques and deep learning methods are used to accurately capture a category of smooth nonlinear system’s spatiotemporal features. The operating point of these systems may change over time, and their nonlinear characteristics can be locally linearized. We established the LSTM-CNN-ARX model by utilizing a fusion of long short-term memory (LSTM) network and convolutional neural network (CNN) to fit the coefficients of the state-dependent exogenous variable autoregressive (SD-ARX) model. Compared to other models, the hybrid LSTM-CNN-ARX model is more effective in capturing the nonlinear system’s spatiotemporal characteristics due to its incorporating the strengths of LSTM for learning temporal characteristics and CNN for capturing spatial characteristics. The model-based predictive control (MPC) strategy, namely LSTM-CNN-ARX-MPC, is developed by utilizing the model's local linear and global nonlinear features. The control comparison experiments conducted on a water tank system (WTS) show the effectiveness of the developed models and MPC methods.

Unmanned Aerial Vehicles (UAV) are increasingly being used in a variety of domains and precision agriculture is no exception. Precision agriculture is the future of agriculture and will play a key role in long-term sustainability of agricultural practices. This paper presents a survey of how image data collected using UAVs has been used in conjunction with ma-chine learning techniques to support precision agriculture. Numerous agricultural applications including classification of crop types and trees, crops detection, weed detection, cropland cover, and segmentation of farming fields are discussed. A variety of supervised, semi-supervised and unsupervised machine learning techniques for image-based preci-sion agriculture are compared. The survey showed that for traditional machine learning approaches, Random Forests performed better than Support Vector Machines (SVM) and K-Nearest Neighbor Algorithm (KNN) for crop/weed classification. And, while Convolutional Neural Networks (CNN) have been used extensively, the U-Net-based models out-performed conventional CNN models for classification and segmentation tasks. Among the Single Stage Detectors (SSD), YOLO series performed relatively well. Two-Stage Detectors like R-CNN, FPN, and Mask R-CNN generally tended to outperform SSDs. Vision Trans-formers (ViT) showed promising results amongst transformer-based models which did not generally perform better than CNNs. Finally, Generative Adversarial Networks (GANs) have been used to address the problem of smaller datasets and unbalanced data

Measuring pulmonary nodules accurately can help with early diagnosis of lung cancer, which can improve a patient’s chances of survival. Many methods for segmenting nodules have been developed, but they all rely on input from radiologists in the form of a 3D volume of interest (VOI) or use a constant region of interest (ROI) and only consider the presence of nodule within the given VOI. These approaches limit the networks’ ability to detect nodules outside the given VOI and can also include unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation by using 2D region of interest (ROI) inputted from radiologist or computer-aided detection (CADe) system. Particularly, we design a dual-encoder-based hard attention network (DEHA-Net) which incorporates the full slice of thoracic computed tomography scan along with the ROI mask to produce an accurate segmentation mask of lung nodule in the given slice. The proposed architecture exploits the adaptive region of interest (A-ROI) algorithm to automatically investigates the penetration of lung nodule into surrounding slices while eliminating the need to drawing separate ROIs in each slice. Further, the framework performs the multi-view analysis, i.e., in sagittal and coronal views, to improve the segmentation performance. The proposed scheme has been rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset and an extensive analysis of results have been performed. The quantitative analysis shows that the proposed method not only improves the existing state-of-the-art in term of dice score but also, significantly robust against the different types, shape and dimensions of lung nodules.

Neural decoding from spiking activity is an essential tool for understanding the information encoded in population neurons, especially in applications like brain-computer interface (BCI). Various quantitative methods have been proposed and have shown superiorities under different scenarios respectively. From the machine learning perspective, the decoding task is to map the high-dimensional spatial & temporal neuronal activity to the low-dimensional physical quantities (e.g., velocity, position). Because of the complex interactions and the abundant dynamics among neural circuits, good decoding algorithms usually have the capability of capturing flexible spatiotemporal structures embedded in the input feature space. Recently, the Transformer-based models are widely used in processing natural languages and images due to its superior performances in handling long-range and global dependencies. Hence, in this work we examine the potential applications of Transformers in neural decoding and introduce two Transformer-based models. Besides adapting the Transformer to neuronal data, we also propose a data augmentation method for overcoming the data shortage issue. We test our models on three experimental datasets and their performances are comparable to the previous state-of-the-art (SOTA) RNN-based methods. In addition, Transformer-based models show increased decoding performances when the input sequences are longer, while LSTM-based models deteriorate quickly. Our research suggests that Transformer-based models are important additions to the existing neural decoding solutions, especially for large datasets with long temporal dependencies.

Multi-floor environments are usually ignored while designing an autonomous robot for indoor cleaning applications. However, for efficient operation in such environments, the ability of a robotic platform to traverse staircases is crucial. Staircase detection and localization is highly important for planning the traversal on staircases. This paper describes a deep learning approach using Convolutional Neural Networks (CNNs) based Robot Operation System (ROS) to staircase detection and localization. We use an object detection network to detect staircases in images. We also localize these staircases using a contour detection algorithm to detect the target point, a point close to the center of the first step, and the angle of approach to the target point. Experiments are performed with data obtained from images captured on different types of staircases at different view points/angles. Results show that the approach is very accurate in identifying the presence of the staircase in the working environment and is also able to locate the target point with good accuracy.

Accurate assessment of the breast cancer deterioration degree plays a crucial role in making medical plan, and the important basis for degree assessment is the number of mitoses in a given area of the pathological image. We utilized deep multi-scale fused fully convolutional neural network (MFF-CNN) combing with conditional random felid (CRF) to detect mitoses in hematoxylin and eosin stained histology image. Analyze the characteristics of mitotic detection ----scale invariance and sparsity, as well as the difficulties ---- small amount of data , inconsistent image staining and sample class unbalanced. Based on this, mitotic detection model is designed. In this paper, a tissue-based staining equalization method is used, and to establish an effective training sample set, we select training samples by using CNN. A mitotic detection model fusing multi-level and multi-scale features and context information was designed, and the corresponding training strategy was made to reduce over-fitting. As preliminarily validated on the public 2014 ICPR MITOSIS data, our method achieves a better performance in term of detection accuracy than ever recorded for this dataset.

Alteration in heparan sulfate (HS) biosynthesis has been described to impact a range of pivotal processes involved in cancer progression. HS 3-O-sulfotransferase 3B1 (HS3ST3B1) catalyzes the reaction of 3-O-sulfation within HS chains. Over the past few years, a growing number of studies has reported a tumor-promoting effect of this HS-modifying enzyme in various cancers. Consistent with these studies, we previously reported that HS3ST3B1 overexpression increased survival and resistance to apoptosis in MDA-MB-231 breast cancer (BrCa) cells. In the present study, we further investigated the biological and clinical significance of HS3ST3B1 expression in BrCa. Interrogation of public databases revealed that high expression levels of HS3STB1 are associated with invasive and mesenchymal-like phenotype in BrCa cells and predict poor clinical outcome in BrCA patients with chemotherapy. In vitro, HS3ST3B1 overexpression increased the invasive properties of MDA-MB-231 cells and enhanced chemo-resistance to conventional anticancer drugs. Mechanistically, we found that the advantage given by HS3ST3B1 was linked to the expression and activation of PDGF-Rβ. Silencing the expression of this receptor reversed the effects driven by HS3ST3B1 overexpression. Altogether, our results suggest that HS3ST3B1 may play an important role in the progression of aggressive BrCa and offer a potentially druggable target for therapeutic application.

With the use of linear regression modeling, this study sought to forecast and analyze rainfall patterns in Ethiopia. The dataset included historical rainfall data as well as pertinent independent variables. The R-squared score and mean squared error (MSE) were used to assess the effectiveness of the linear regression model. The results showed that the model's ability to forecast and analyze rainfall patterns was not very good. Only around 5.3% of the variance in rainfall could be explained by the chosen independent variables, according to the R-squared score of 0.053. This low number indicated that there was little correlation between the selected variables and rainfall, and that a sizable percentage of the variation in the dependent variable was not captured by the model. The model's accuracy in forecasting rainfall was shown to be quite low by the MSE error, with significant squared discrepancies between the expected and actual amounts. These results support the notion that the linear regression model as it is now designed is not appropriate for studying or forecasting Ethiopia's rainfall patterns. Alternative modeling approaches, the inclusion of other pertinent factors, and the assurance of the availability of high-quality data that faithfully captures the intricate dynamics of rainfall in the area all require more investigation.

The quadratic unconstrained binary optimization (QUBO) is a classic NP-hard problem with an enormous number of applications. Local search strategy (LSS) is one of the most fundamental algorithmic concepts that has been successfully applied to a wide range of hard combinatorial optimization problems. One LSS that has gained the attention of researchers is the r-flip (also known as r-Opt) strategy. Given a binary solution with n variables, the r-flip strategy ‘flips’ r binary variables to get a new solution if the changes improve the objective function. The main purpose of this paper is to develop several results for implementation of r-flip moves in QUBO, including a necessary and sufficient condition that when a 1-flip search reaches local optimality, the number of candidates for implementation of the r-flip moves can be reduced significantly. The results of the substantial computational experiments are reported to compare an r-flip strategy embedded algorithm and a multiple start tabu search algorithm on a set of benchmark instances and three very-large-scale QUBO instances. The r-flip strategy implemented within the algorithm makes the algorithm very efficient, very high-quality solutions within a short CPU time.

This paper introduces the spatial component in cross-section econometric estimations and specifically, the spatial dependence effect inherent in some of the variables involved in the modelling process. First, the spatial structure of the data from thematic maps is observed and Moran's spatial autocorrelation indicators are presented. Subsequently, the spatial weights matrix is built under different specifications. Finally, several modelling specification strategies are shown and the interpretation of the estimated coefficients. The theoretical concepts are illustrated with examples and their corresponding R software codes. This code and databases are available in a freely accessible repository in the BE2SHARE-EUDAT platform so that they can be easily reproduced.

Studies on the neurobiological causes of anxiety disorders suggest that the GABA system in-creases synaptic concentration and enhances the affinity of GABAA (type A) receptors for ben-zo-diazepine ligands. Flumazenil antagonizes the benzodiazepine binding site of the GABA (γ-aminobutyric acid) type /benzodiazepine receptor (BZR) complex in the central nervous sys-tem (CNS). The integration of the metabolites of flumazenil by LC-tandem mass spectrometry will complete understanding of the in vivo metabolism of flumazenil and accelerate radio-pharmaceutical inspection and registration. The main goal of our study was to investigate using reversed-phase HPLC (PR-HPLC) coupled with electrospray ionization triple quadrupole tan-dem mass spectrometry (ESI-QqQ MS) for the identification of flumazenil and its metabolites in a hepatic matrix. And a carrier-free nucleophilic fluorination with automatic synthesizer for [18F]flumazenil which applied to in vivo nano-positron emission tomography (Nano-PET)/computed tomography (CT) imaging and ex vivo bio-distribution used to analyze in normal rats. The study showed that 50% of the flumazenil was bio-transformed at 60 min by the rat liver homogenate, while one metabolite (M1) was a methyl transesterification product of flumazenil. In a rat liver microsomes system, two metabolites were identified (M2 and M3) as its carboxylic acid and hydroxylated ethylester forms, respectively. [18F]flumazenil in vivo nanoPET/CT imag-ing and ex vivo bio-distribution assay also showed significant effects on GABAA receptor availa-bility in the amygdala, prefrontal cortex, cortex, and hippocampus in the rat brain, worriless about the formation of metabolites. We showed completion of the bio-transformed course of flumazenil by the hepatic system; and [18F]flumazenil can be a good ligand and serve as a PET agent for determination of GABAA/BZR complex for multiplex neurological syndromes in the clinical stage.

This study investigated whether export performance is correlated with innovation. We explicitly considered five types of innovation: a) process innovation; b) product innovation; c) process and product innovation; d) product innovation new to the firm; and e) product innovation new to the market. We en-larged the findings of R&D-export and R&D-investment relations using a vast sample of cross-European firms. We considered innovation as endogenous and determined by R&D through a process characterized by the role of the regional technological environment. Our analysis enabled us to propose an integrated model incorporating R&D, innovation and export, in a framework of simultaneous equations which consider their mutual correlations. To the best of our knowledge, this work is the first in recent years to empirically compute the relation between R&D and tangible investment at the micro level. Econometric results showed that product and process innovation are positively linked to the export intensity of European manufacturing firms. The results also showed complementarity effects between the two kinds of innovation. The av-erage effect on export intensity from carrying out process innovation is larger than that found for product innovation, except in cases where the product is new to the market. When both types of innovation have been carried out, a larger effect results than that found for product or process innovation alone. Furthermore, the average marginal effect on export intensity from innovations of any kind among those studied here is highly positive and significant.

We obtain exact solutions to the field equations for 5 dimensional LRS Bianchi type-I spacetime in $f(R,T)$ theory of gravity where specifically the following three cases are considered: (i) $f(R,T)=\mu(R+T)$, (ii) $f(R,T)=R \mu + R T \mu^2$ and (iii) $f(R,T)=R+\mu R^2+\mu T$ where $R$ and $T$ respectively the Ricci scalar and trace of the energy-momentum tensor. It is found that the equation of state (EOS) parameter $w$ is governed by the parameter $\mu$ involved in the $f(R,T)$ expressions. We fine-tune the parameter $\mu$ to obtain effect of phantom energy in the model, however we also restrict this parameter to obtain a stable model of the universe. It is noted that the model isotropizes at finite cosmic time.

This paper is related to the fractional view analysis of Helmholtz equations, using innovative analytical techniques. The fractional analysis of the proposed problems has been done in terms of Caputo-operator sense. In the current methodology, first, we applied the r-Laplace transform to the targeted problem. The iterative method is then implemented to obtain the series form solution. After using the inverse transform of the r-Laplace, the desire analytical solution is achieved. The suggested procedure is verified through specific examples of the fractional Helmholtz equations. The present method is found to be an effective technique having a closed resemblance with the actual solutions. The proposed technique has less computational cost and a higher rate of convergence. The suggested methods are therefore very useful to solve other systems of fractional order problems.

G-quadruplexes are noncanonical nucleic acid structures formed from stacked guanine tetrads. They are frequently used as building blocks and functional elements in fields such as synthetic biology and also thought to play widespread biological roles. G-quadruplexes are often studied as monomers but can also form a variety of higher-order structures. This increases the structural and functional diversity of G-quadruplexes, and recent evidence suggests that it could also be biologically important. In this review we describe the types of multimeric topologies adopted by G-quadruplexes and highlight what is known about their sequence requirements. We also summarize the limited information available about potential biological roles of multimeric G-quadruplexes and suggest new approaches that could facilitate future studies of these structures.

The aim of this study was to analyze whether the respiratory variation in ECG standard lead II R-wave amplitude (ΔRDII) could be used to assess intravascular volume status following inferior vena cava (IVC) clamping. This clamping causes an acute decrease in cardiac output during liver transplantation (LT). We retrospectively compared ΔRDII and related variables before and after IVC clamping in 34 recipients. Receiver operating characteristic (ROC) curve and area under the curve (AUC) analyses were used to derive a cutoff value of ΔRDII for predicting pulse pressure variation (PPV). After IVC clamping, cardiac output significantly decreased while ΔRDII significantly increased (P = 0.002). The cutoff value of ΔRDII for predicting a PPV >13% was 16.9% (AUC: 0.685) with a sensitivity of 57.9% and specificity of 77.6% (95% confidence interval 0.561 – 0.793, P = 0.015). Frequency analysis of ECG also significantly increased in the respiratory frequency band (P = 0.016). Although significant changes in ΔRDII during vena cava clamping were found at norepinephrine doses < 0.1 μg/kg/min (P = 0.014), such changes were not significant at norepinephrine doses > 0.1 μg/kg/minP = 0.093). ΔRDII could be a noninvasive dynamic parameter in LT recipients presenting with hemodynamic fluctuation. Based on our data, we recommended cautious interpretation of ΔRDII may be requisite according to vasopressor administration status.

There are no studies that quantitatively compare life histories among scorpion species. Statistical procedures applied to 94 scorpion species indicate that those with larger bodies do not necessarily have larger litters or longer life cycles, opposite to some theoretical predictions.

This study explores novel techniques to improve the detection accuracy of skarn iron deposits using advanced image processing methodologies. Leveraging the capabilities of Aster image, Band Ratio (BR) images, and Principal Component Analysis (PCA), alongside the power of 3D Convolutional Neural Networks (3D-CNN), the research aims to enhance the precision and efficiency of ore detection in complex geological environments. The proposed method employs a specific 3D-CNN architecture, accepting input as a 7×7×C image patch, where C represents the combined number of selected Aster image bands, Principal Component (PC) bands, and computed BR images. To evaluate the accuracy of the proposed method, five distinct image bands combinations, including the proposed bands combination, were tested and evaluated based on the overall accuracy (OA), average accuracy (AA), and kappa coefficient. The results demonstrated that while the incorporation of BR images alongside Aster bands initially seemed promising, it introduced significant confusion in certain classifications, leading to unexpected mis-classification rates. Surprisingly, utilizing solely Aster bands as input parameters yielded higher accuracy rates (OA= 93.13%, AA = 91.96%, Kappa = 90.91%) compared to scenarios involving the integration with band ratios (OA = 87.02%, AA = 79.15, and Kappa = 82.60%) or the integration of BR images to PC bands (OA= 87.78%, AA = 82.39%, Kappa = 83.81%). However, the amalgamation of Aster bands with selected PC bands showed slight improvements in accuracy (OA= 94.65%, AA = 92.93%, Kappa = 93.45%), although challenges in accurately classifying certain features persisted. Ultimately, the proposed combination of Aster bands, PC bands, and BR images (proposed bands combination) presented the most visually appealing and statistically accurate results (OA = 96.95%, AA= 94.87%, and Kappa = 95.93%), effectively addressing misclassifications observed in the other combinations. These findings underscore the synergistic contributions of each of the Aster bands, PC bands, and BR images, with Aster bands proving pivotal for optimal skarn classification, PC bands enhancing intrusions classification accuracy, and BR images strengthening wall rock classification accuracy. In conclusion, the proposed combination of input image bands emerges as a robust and comprehensive methodology, demonstrating unparalleled accuracy in the remote sensing detection of skarn iron minerals.

The continuous advancements in healthcare technology have empowered the discovery, diagnosis, and prediction of diseases, revolutionizing the field. Artificial intelligence (AI) is expected to play a pivotal role in achieving the goals of precision medicine, particularly in disease prevention, detection, and personalized treatment. This study aims to determine the optimal combination of the mother wavelet and AI model for the analysis of pediatric electroretinogram (ERG) signals. The dataset, consisting of signals and corresponding diagnoses, undergoes Continuous Wavelet Transform (CWT) using commonly used wavelets to obtain a time-frequency representation. Wavelet images were used for the training of five widely used deep learning models: VGG-11, ResNet-50, DensNet-121, ResNext-50, and Vision Transformer, to evaluate their accuracy in classifying healthy and unhealthy patients. The findings demonstrate that the combination of Ricker Wavelet and Vision Transformer consistently yields the highest median accuracy values for ERG analysis, as evidenced by the upper and lower quartile values. The median balanced accuracy of the obtained combination of the three considered types of ERG signals in the article are 0.83, 0.85, and 0.88. However, other wavelet types also achieved high accuracy levels, indicating the importance of carefully selecting the mother wavelet for accurate classification. The study provides valuable insights into the effectiveness of different combinations of wavelets and models in classifying ERG wavelet scalograms.

The problem of health status prediction of insulated-gate bipolar transistors (IGBTs) gains a lot of attention in the field of health management of power electronic equipment. The performance degradation of IGBT gate oxide layer is one of the important failure modes. In view of failure mechanism analysis and easy implementation of monitoring circuit, this paper selects the gate leakage current of IGBT as the precursor parameter of gate oxide degradation, and uses time domain characteristic analysis, gray correlation degree, Mahalanobis distance, Kalman filter and other methods to carry out feature selection and fusion, and finally obtains a health indicator characterizing the degradation of IGBT gate oxide. Based on the Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) network, this paper constructs an IGBT gate oxide degradation prediction model, and performs experimental analysis on the dataset released by NASA-Ames Laboratory, and the average absolute error of performance degradation prediction is as low as 0.0216. Compared with Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Support Vector Regression (SVR) and CNN-LSTM models, CNN-LSTM network has the highest prediction accuracy. These results show the feasibility of gate leakage current as a precursor parameter of IGBT gate oxide layer failure, as well as the accuracy and reliability of the CNN-LSTM prediction model.

In the last few decades, glaucoma became the second biggest leading cause of irreversible vision loss. Because of its asymptotic growth, it is not properly diagnosed until the relatively late stage. To stop the severe damage by glaucoma it is needed to detect glaucoma in its early stages. Surprisingly diabetes also be the greatest cause of glaucoma. In the modern era, artificial intelligence makes great progress in the medical image processing field. Image analysis based on machine learning gives a huge success in diagnosis glaucoma without any misdiagnosis. The aim of this proposed paper is to create an automated process that can detect glaucoma and diabetic retinopathy. Here various Machine Learning models are used and results of these methods are presented.

The diagnosis of a rolling bearing for monitoring its status is critical for maintaining industrial equipment using rolling bearings. The traditional method of diagnosing faults of the rolling bearing has low identification accuracy, which needs artificial feature extraction to enhance the accuracy. 1D-CNN method not only can diagnose bearing faults accurately but also overcome shortcomings of the traditional methods. Different from machine learning and other deep learning models, the 1D-CNN method does not need pre-processing one-dimensional data of rolling bearing’s vibration. Thus, it enhances the processing speed and improves the network structure to have a reasonable design for small sample data sets. This study proposes and tests a 1D-CNN method for diagnosing rolling bearings. By introducing the dropout operation, the method obtains high accuracy and improves the generalizing ability. The experimental results show 99.52% of the average accuracy under a single load and 98.26% under different loads.

Accurate and efficient traffic incident detection methods can effectively alleviate traffic congestion caused by traffic incidents, prevent secondary accidents and improve the safety of urban road traffic.Aiming at the problems that the traditional machine learning event detection method cannot fully extract the parameter characteristics of traffic flow and is not suitable formulti-dimensional and non-linear massive data, we propose a new traffic event detection method(CNN-XGBoost).This method combines the respective advantages of Convolution Neural Network(CNN) and Extreme Gradation Boosting (XGBoost). Firstly, we preprocessed the original freeway traffic incident detection data set by constructing initial variable set, data normalization, data balance processing and dimension reorganization. Secondly,we use CNN network to automatically extract the deep features of event detection data, and use XGBoost as a classifier to classify the extracted features for expressway traffic event detection.Finally, we use the data set of Hangzhou expressway microwave detector in China to carry out simulation experiments on CNN-XGBoost. The experimental results show that compared with XGBoost, CNN, Support Vector Machine (SVM) and Gradient Boosting Decision Tree (GBDT) and other methods, CNN-XGBoost method can effectively improve the accuracy of expressway traffic event detection and has better generalization ability.

Detection of the region of interest (ROI) is a critical step in laryngeal image analysis for the delineation of glottis contour. The process can improve both computational efficiency and accuracy of the image segmentation task, which will facilitate subsequent analysis and characterization of the vocal fold vibration as it correlates with voice quality and pathology. This study aims to develop machine learning based approaches for automatic detection of ROI for glottis image sequences captured by high-speed video-endoscopy (HSV), a clinical laryngeal imaging modality. In particular, we first applied the supporting vector machine (SVM) method using histogram of oriented gradients (HOG) feature descriptor, and second, trained a convolutional neural network (CNN) model for this task. Comparisons are made for both approaches in terms of accuracy of recognition and computation time.

To improve the tangerine crop yield, the work of recognizing and then disposing of specific pests is becoming increasingly important. The task of recognition is based on the features extracted from the images that have been collected from websites and outdoors. Traditional recognition and deep learning methods, such as KNN (k-nearest neighbors) and AlexNet, are not preferred by knowledgeable researchers, who have proven them inaccurate. In this paper, we exploit four kinds of structures of advanced deep learning to classify 10 citrus pests. The experimental results show that Inception-ResNet-V3 obtains the minimum classification error.

Preliminaries Convolutional Neural Network (CNN) applications have recently emerged in Structural Health Monitoring (SHM) systems focusing mostly on vibration analysis. However, the SHM literature shows clearly that there is a lack of application regarding the combination of PZT (Lead Zirconate Titanate) based method and CNN. Likewise, applications using CNN along with the Electromechanical Impedance (EMI) technique applied to SHM systems are rare. To encourage this combination, an innovative SHM solution through the combination of the EMI-PZT and CNN is presented here. To accomplish this, the EMI signature is split into several parts followed by computing the Euclidean distances among them to form a RGB (red, green and blue) frame. As a result, we introduce a dataset formed from the EMI-PZT signals of 720 frames, encompassing a total of 4 types of structural conditions for each PZT. In a case study, the CNN-based method was experimentally evaluated using three PZTs glued onto an aluminum plate. The results reveal an effective pattern classification; yielding a 100% hit rate which outperforms other SHM approaches. Furthermore, the method needs only a small dataset for training the CNN, providing several advantages for industrial applications.

In the early 2000s, matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) emerged as a performant and relevant tool for identifying micro-organisms. Since then, it has become practically essential for identifying bacteria in microbiological diagnostic laboratories. In the last decade, it was successfully applied for arthropod identification allowing to distinguish vectors from non-vectors of infectious diseases. However, identification failures are not rare, hampering it widely use. Failure is generally attributed either to the absence of respective counter species MS spectra in the database, or to the insufficient quality of query MS spectra (i.e. lower intensity and diversity of MS peaks detected). To avoid matching errors due to non-compliant spectra, the development of a strategy for detecting and excluding outlier MS profiles became compulsory. To this end, we created MSProfileR, an R package leading to a bioinformatics tool through a simple installation, integrating the control quality system of MS spectra and an analysis pipeline including peak detection and MS spectra comparisons. MSProfileR can also add metadata concerning the sample that the spectra are derived from. MSProfileR has been developed in the R environment and offers a user-friendly web interface using the R Shiny framework. It is available on Microsoft Windows as a web browser application by simply navigation using the link of the package on the Github. MSProfileR is therefore accessible to non-computer specialists and is freely available to the scientific community. We evaluated MSProfileR using two datasets including exclusively MS spectra from arthropods. In addition to coherent sample classification, outlier MS spectra were detected in each dataset confirming the value of MSProfileR.

This paper provides a first-time ever unification of information theory, semi-group theory with the theory of uncertain reasoning, through functional perspective. Fundamentally, the threshold theorems for the inference functional were devised. Furthermore, numerical experiments are illustrated. The complex proofs in our paper are original results which emphasizes the credibility of the class of Rényi Generalized Entropies as measures of information, and that the field is open to extend an enhanced methodology regarding queuing networks with heavy tails.

In this paper, we have established some new bounds of Fejér type Hermite-Hadamard inequality for k−fractional integrals involving r−times differentiable preinvex functions. It is noteworthy that in the past there was no weighted version of left and right sides of the Hermite-Hadamard inequality for k-fractional integrals for generalized convex functions available in literature.

Background: This work aimed to undertake a bibliometric analysis of the Rubella virus. Medical studies were conducted between 2000 and 2022 to discover trends, dynamics, and research outputs in the industry. Methods:A bibliometric study was performed using R software to determine research characteristics indexed worldwide and published in Rubella research in medical studies. The Rubella virus was chosen as the subject in the PUBMED database, and 374 papers from the previous two decades were reviewed. Results: There was an increase in the number of publications after 2003. The United States was the most essential countryamong all which had the most contributions on Rubella Virus. Conclusion:Rubella research has increased in the medical profession over the previous decade, with the United States leading to publications in this field.

This study aims to test empirical research on the effect of financial resource ability, research and development (R &amp; D) on innovation orientation and competitive position. This study also examines the critical mediating role of innovation orientation and competitive position to achieving new products performance (NPP). This study used a quantitative research approach by comparing data from service industry and manufacture industry in Indonesia included in Indonesian-State-Ownership companies. The analysis unit in this study used middle managers and top managers who responsible for managing divisions within the Indonesian-State-Ownership companies. The number of respondents studied in this study was 287 sample. The purposive sampling technique was used in taking the research sample. This study indicated that financial resources abilities, research and development (R &amp; D) abilities positive effect on innovation orientation and competitive position. This study also testing the importance role of innovation orientation and a competitive position to enhancing new products performance (NPP).

Context: COVID-19 pandemic and the Lockdown implemented as a measure to contain the virus spread has taken a toll over the psychological well-being of the people especially the young adults, the confinement along with the environment of a highly infectious pandemic around the induvial are put under great stress.Aims: The current study aims to assess the psychological impact and perceived stress due to COVID-19 lockdown in Young Adult population of India.Settings and Design: It is a cross sectional, observational study.Methods and Material: The survey was conducted using Google forms involving snowball sampling technique which obtained 267 responses in total. (IES-R) and (PSS) scales were used for the study.Statistical analysis used: Descriptive analysis were performed on the sociodemographic parameters and the comparison of means were done by Chi-square test in SPSS Statistic 21.0 (IBM SPSS Statistics, New York, United States). Results: The mean IES-R and PSS scores obtained for the population in this study was 25.64±18.95 and 18.27±6.10 respectively. Out of the 267 respondents in total 61.4% (n=164) of them were males. Maximum of the respondents 62.54%(n=167) belonged to the age group of 18-23 with mean age being 23.14± 2.913. 92.5% of the respondents were unmarried and only 26.6% belonged to the rural part of India. Females, younger individuals were found to have higher IES-R and PSS scores. Conclusions: There is significant psychological burden and stress on the young Indian population with females and younger individuals particularly students are the most vulnerable population.

In the promptness of the COVID-19 outbreak, it would be very important to observe and estimate the pattern of diseases to reduce the contagious infection. To study this effect, we developed a COVID-19 epidemic model that incorporates five various groups of individuals. Then we analyze the model by evaluating the equilibrium points and analyzing their stability as well as determining the basic reproduction number. Also, numerical simulations show the dynamics of a different group of the population over time. Thus, our findings based on the sensitivity analysis and the reproduction number highlight the role of outbreak of the virus that can be useful to avoid a massive collapse in Bangladesh and rest of the world. The outcome of this study concludes that outbreak will be in control which ensure the social and economic stability.

In this study, regression analyses were used to find a relationship between the rain gauge rainfall rate R and radar reflectivity Z for the urban catchment of the Służewiecki Stream in Warsaw, Poland. Rainfall totals for 18 events which were measured at two rainfall stations were used for these analyses. Various methods for determining calculational values of radar reflectivity in reference to specific rainfall cells with 1-km resolution within an event duration were applied. The influence of each of these methods on the Z-R relationship was analyzed. The correction coefficient for data from the SRI (Surface Rainfall Intensity) product was established, in which the values of rainfall rate are calculated based on parameters a and b determined by Marshall and Palmer. Relatively good agreement between measured and estimated rainfall totals for the analyzed events was obtained using the Z-R relationships as well as the correction coefficient determined in this study. Rainfall depths estimated from radar data for two selected events were used to simulate flow hydrographs in the catchment using the SWMM (Storm Water Management Model) hydrodynamic model. Different scenarios were applied to investigate the stream response to changes in rainfall depths, in which the data both for 2 existing as well as 64 virtual rain gauges assigned to appropriate rainfall cells in the catchment were included.

The necessity for effective intrusion detection systems (IDS) in big data environments has grown critical due to the rising prevalence of big data systems and the rising amount of security threats. Applying conventional intrusion detection methods to the enormous and intricate data produced by big data ecosystems presents difficulties. Deep learning, has proven to be exceptionally adept at deciphering complex, large-scale data. This study proposes a Deep Learning-based Intrusion Detection System (IDS) created specifically for the Big Data environment. Traditional intrusion detection systems struggle to efficiently identify and prevent cyber threats due to the ever-increasing volume and complexity of data in current networks. We suggest an IDS that makes use of Deep Learning (CNN, LSTM, GAN, etc.), to address this problem. These cutting-edge neural network topologies give the system the ability to process and analyze massive amounts of data for precise intrusion detection. Data collection, data preprocessing, feature engineering, DL model training, intrusion detection, warning generation, and reaction are some of the crucial parts of the suggested IDS. The data collection module mines the Big Data environment for network traffic, system logs, and security event information. To make sure the data is suitable for analysis, it is preprocessed. To improve the detection abilities of the DL models, important features are extracted from the data using feature engineering approaches.

In recent years, Synthetic Aperture Radar (SAR) has received attention in the Automatic Target Recognition (ATR) field due to its ability to acquire images both day and night, combined with the superior resolution offered by the latest sensors. However, despite advances, there remains a deficiency in dataset quality and quantity. This has necessitated the use of simulated data to overcome challenges associated with obtaining large quantities of high-quality images of targets and their subsequent labeling. In this study, we trained a Convolutional Neural Network (CNN) using a simulated dataset, subsequently employing it to classify real images from the MSTAR dataset. Traditional training methodologies often struggle with generalization when confronted with domain disparities between simulated and real data. To mitigate this, we exploited Margin Disparity Discrepancy (MDD), a domain adaptation technique not previously explored in SAR context. Findings from this study showcased a 13% increase in classification accuracy and improved generalization using MDD. Through Explainable AI (XAI) techniques such as t-SNE and other metrics like Kullback Leibler Divergence (KLD), we revealed a more distinct alignment of feature spaces between the two domains after domain adaptation, emphasizing MDD’s role in enhancing model accuracy and generalization.

Abstract: The surge of diabetes poses a significant global health challenge, particularly in Oman and the Middle East. Early detection of diabetes is crucial for proactive intervention and improved patient outcomes. This research leverages the power of machine learning, specifically, Convolutional Neural Networks (CNNs), to develop an innovative 4D CNN model dedicated to early diabetes prediction. A region-specific dataset from Oman is utilized to enhance health outcomes for individuals at risk of developing diabetes. The proposed model showcases remarkable accuracy, achieving an average accuracy of 98.49% to 99.17% across various epochs. Additionally, it demonstrates excellent F1 score, recall, and sensitivity, highlighting its ability to identify true positive cases. The findings contribute to the ongoing effort to combat diabetes and pave the way for future research in using deep learning for early disease detection and proactive healthcare.

Automatic target detection of remote sensing images (RSI) plays an important role in military reconnaissance, disaster monitoring, and target rescue. The core task of remote sensing target detection is to judge the target categories and complete precise location. However, the existing target detection algorithms have limited accuracy and weak generalization capability for remote sensing images with complex backgrounds. To achieve accurate detection of different categories targets in remote sensing images, this study presents a novel feature enhancement single shot multibox detector (FESSD) algorithm for remote sensing target detection. The FESSD introduces feature enhancement module and attention mechanism into the convolution neural networks (CNN) model, which can effectively enhance the feature extraction ability and nonlinear relationship between different convolution features. Specifically, the feature enhancement module is used to extract the multi-scale feature information, and enhance the model nonlinear learning ability; the self-learning attention mechanism (SAM) is used to expand the convolution kernel local receptive field, which makes the model extract more valuable features. In addition, the nonlinear relationship between different convolution features is enhanced using the feature pyramid attention mechanism (PAM). The advantage of FESSD over other state-of-the-art target detection methods is validated by experiments on the presented seven-class target detection dataset (SD-RSI) and the public DIOR dataset.

High costs for the repair of concrete structures can be prevented if damage at an early stage of degradation is detected and precautionary maintenance measures are applied. To this end, we use numerical wave propagation simulations to identify simulated damage in concrete using convolutional neural networks (CNN). Damage in concrete subjected to compression is modeled at the mesoscale using the discrete element method. Ultrasonic wave propagation simulation on the damaged concrete specimens are performed using the rotated staggered finite-difference grid method. The simulated ultrasonic signals are used to train a CNN based classifier capable of classifying three different damage stages (microcrack initiation, microcrack growth and microcrack coalescence leading to macrocracks). The performance of the classifier is improved by refining the dataset via an analysis of the averaged envelope of the signal. The classifier using the refined dataset has an overall accuracy of 90%.

The automatic recognition of scanned Medieval manuscripts still represents a challenge due to degradation, non standard layouts, or notations. This paper focuses on the Medieval square notation developed around the 11th century which is composed of staff lines, clefs, accidentals, and neumes which are basically connected single notes. We present a novel approach to tackle the automatic transcription by applying CNN/LSTM networks that are trained using the segmentation-free CTC-loss-function which considerably facilitates the GT-production. For evaluation, we use three different manuscripts and achieve a dSAR of 86.0% on the most difficult book and 92.2% on the cleanest one. To further improve the results, we apply a neume dictionary during decoding which yields a relative improvement of about 5%.

Partial Information Decompositions (PIDs) aim to categorize how a set of source variables provide information about a target variable redundantly, uniquely, or synergetically. The original proposal for such an analysis used a lattice-based approach and gained significant attention. However, finding a suitable underlying decomposition measure is still an open research question, even at an arbitrary number of discrete random variables. This work proposes a solution to this case with a non-negative PID that satisfies an inclusion-exclusion relation for any f-information measure. The decomposition is constructed from a pointwise perspective of the target variable to take advantage of the equivalence between the Blackwell and zonogon order in this setting. The zonogons correspond to the Neyman-Pearson region for an indicator variable of one target state and f-information is the expected value of quantifying its boundary. We prove that the decomposition satisfies the axioms of the original decomposition framework and guarantees non-negative partial information results. We highlight that our decomposition behaves differently depending on the used information measure, which can be utilized for different applications. We additionally show how our proposal can be used to obtain a non-negative decomposition of Rényi-information at a transformed inclusion-exclusion relation, and for tracing partial information flows through Markov chains.

This article presents the graphical user interface of the ACUX-R mobile recommendation system, tailored for the cultural tourism domain. ACUX-R offers personalized recommendations based on visiting preferences, augmenting the overall user experience. Building upon a comprehensive methodology and recommendation algorithms from previous work, this contribution focuses on the user interface aspects of the ACUX-R by highlighting key design considerations, user interface elements and functionalities that contribute to an effective and engaging user experience. In an effort to evaluate the proposed interface, an initial case study with a dataset consisting of points of interest from the City of Athens, Greece has been performed. In the framework of the aforementioned study, the proposed user interface attained high ratings with respect to inspiring, exciting, interesting, and enthusiastic user experiences.

A locally-rotationally-symmetric Bianchi-I model filled with strange quark matter (SQM) is explored in f(R, T) gravity. We take f(R, T) = R + 2 f(T) = R + 2λT, where R is the Ricci scalar, T is the trace of energy-momentum tensor and λ is an arbitrary constant. Exact solutions are obtained by assuming that the expansion scalar is proportional to the shear scalar. This yields a constant value for the deceleration parameter, q = 2, which corresponds to the decelerated phase of the universe. The model is found to be physically viable for λ < −1. SQM during early evolution mimics ultra-relativistic radiation whereas at late times, it behaves as dust, quintessence or even the cosmological constant depending on the value of λ. The effective matter acts as a stiff fluid irrespective of the matter content and of the f(R, T) terms. The model is shear free at late times but remains anisotropic throughout the evolution. In the absence of the f(R, T) terms, SQM accelerates the universe. In the specific case when SQM vanishes at late times, the effect of f(R, T) is to accelerate the universe. The model admits the possibility that SQM could be an alternative to dark energy.

Green credit policy as an important tool to guide China's sustainable economic development, how to effectively play the function of capital deployment and improve the efficiency of industrial green innovation is an important issue facing the construction of ecological civilization. This paper uses China's Green Credit Guideline introduced in 2012 as a quasi-natural experiment , based on relevant panel data of industries from 2007 to 2018, uses the Super-SBM model including non-expected output to measure the green innovation efficiency of 35 industries in China, and constructs the PSM-DID model to explore how green credit policy impact on the green innovation efficiency of heavily polluted industries, the results show that : green credit policy significantly contributes to green innovation efficiency of heavily polluted industries with a lag. Further study finds that green credit policy pushes heavily polluted industries to improve green innovation efficiency by increasing financing cost and R&D investment; meanwhile, the heterogeneity test shows that the higher the state-owned share of industry, the greater the promoted effect of green credit policy on green innovation efficiency of heavily polluted industries. Finally, in order to accelerate the implementation of green credit policy and promote the green innovation efficiency of heavily polluted industries, relevant countermeasures are proposed from three aspects: banks, enterprises and government.

Due to the continuous trade friction between China and the United States, for domestic enterprises in China, the cost of importing foreign technologies is increasing. Thus, the independent research and development (R&D) becomes particularly important for the realization of green technology innovation (GTI). This paper establishes a non-linear mediating effect model based on the data of various regions in China from 2012 to 2018. The main results are shown in the following. Firstly, there is an inverted U-shaped relationship between the intensity of intellectual property protection (IPP) and the level of GTI. Furthermore, the independent R&D investment has a masking effect between them. Secondly, by taking the independent R&D investment as a threshold variable, we prove our findings. Considering that the intensity of IPP is at a high level in most regions of China, the above statements mean that the enterprises need to continuously increase their investment in R&D, in order to further improve the regional ability in GTI. Meanwhile, local governments should also stimulate enterprises' willingness to expand their scale in R&D by issuing incentive policies, such as R&D tax incentives and government subsidies.

Background & Objectives: The global pandemic caused by novel coronavirus SARS-CoV-2 has claimed several lives worldwide. With the virus gathering rapid spread, the world has witnessed increasing number of confirmed cases and mortality rate, India is not far behind with approximately 37,000 affected individuals as on May 2, 2020. The ongoing pandemic has raised several questions which need to be answered by analysis of transmission of the infection. The data has been collected on daily basis from WHO and other sites. We have represented the data collated graphically using statistical packages, R and other online softwares. The present study provides a holistic overview of the spread of COVID-19 infection in India. Methods: Real-time data query was done based on daily observations using publicly available data from reference websites for COVID-19 and other government official reports for the period (15^th February, 2020 to April 28^th, 2020). Statistical analysis was performed to draw important inferences regarding COVID-19 trend in India. Results: A decrease in growth rate of cases due to COVID-19 in India post lockdown and improvement in recovery rate during the month of April was identified. The case fatality rate was estimated to be 3.22% of the total reported cases. State-wise analysis revealed a deteriorating situation in states of Maharashtra and Gujarat among others as cases continued to increase rapidly there. A positive linear correlation between the number of deaths and total cases and exponential relation between population density and number of cases reported per square km was established. Interpretation & Conclusions: Despite early preventive measures taken up by the Government of India, the increasing number of cases in India is a concern. This study compiles state-wise and district-wise data to report the daily confirmed cases, case fatalities and strategies adopted in the form of case studies. Understanding the transmission spread of SARS-CoV-2 in a diverse and populated country like India will be crucial in assessing the effectiveness of control policies towards the spread of COVID-19 infection.

The “NWCSAF High Resolution Winds (NWC/GEO-HRW)” software is developed by the EUMETSAT’s “Satellite Application Facility on support to Nowcasting and very short range forecasting (NWCSAF)”, inside its stand-alone software package for calculation of meteorological products with geostationary satellite data (NWC/GEO). The whole NWC/GEO software package can be obtained after registration at the NWCSAF Helpdesk, www.nwcsaf.org. It is easy to get, install and use. The code is easy to read and fully documented. And in the NWCSAF Helpdesk, users find support and help for its use. “NWCSAF High Resolution Winds” provides a detailed calculation of Atmospheric Motion Vectors (AMVs) and Trajectories, locally and in near real time, using as input NWP model data and geostationary satellite image data. The latest version of the software, v2018, is able to process MSG, Himawari-8/9, GOES-N and GOES-R satellite series images, so that AMVs and Trajectories can be calculated all throughout the planet Earth with the same algorithm and quality. In the “2014 and 2018 AMV Intercomparison Studies”, “NWCSAF High Resolution Winds” has shown to be one of the two best AMV algorithms for both MSG and Himawari-8/9 satellites. And the “Coordination Group for Meteorological Satellites (CGMS)” has recognized in its “2012 Meeting Report”: 1. “NWCSAF High Resolution Winds” fulfills the requirements to be a portable stand-alone AMV calculation software due to its easy installation and usability. 2. It has been successfully adapted by some CGMS members and serves as an important tool for development. It is modular, well documented, and well suited as stand-alone AMV software. 3. Although alternatives exist as portable stand-alone AMV calculation software, they are not as advanced in terms of documentation and do not have an existing Helpdesk. Considering this, a full description and validation of the “NWCSAF/High Resolution Winds” is shown here for the first time in a peer-reviewed paper. The procedure to obtain the software for operational meteorology and research is also explained.

The spectra currently emerging from modern ground- and space-based astronomical instruments are of exceptionally high quality and resolution. To meaningfully analyse these spectra researchers utilise complex modelling codes to replicate the observations. The main inputs to these codes are atomic data such as excitation and photoionisation cross sections as well as radiative transition probabilities, energy levels and line strengths. In this publication the current capabilities of the numerical methods and computer packages used in the generation of these data are discussed. Particular emphasis is given to Fe-peak species and the heavy systems of tungsten and molybdenum. Some of the results presented to highlight certain issues and/or advances have already been published in the literature, while other sections present, for the first time, new recently evaluated atomic data.

Facial recognition systems are widely used systems around the globe. Their applications in real world scenarios like law enforcement, surveillance, ID card identification, information security, access control and many more has made them very important in today’s world. These systems have shown promising results and excellent performance; however, these systems need tremendous number of facial images for training before they are implemented in the real-world scenarios. The problem arises when we face lack of training images due to which the performance of such systems decreases exponentially. The problem becomes even worse when there is only one image per subject for training our facial recognition system, the probe image might contain variation like illumination, expression and disguise which are hard to be accurately recognized. Generative models have achieved great success for handling the lack of training data by generating synthetic data that resembles the original data. We have created a new method by fine tuning the basic Conditional Generative Adversarial Network (CGAN) to generate synthetic facial images provided only single image per subject. These synthetic facial images contain six variations that are smile, anger, stare, illumination and disguise. We increased the size of the dataset and then applied a convolutional neural network for facial recognition, which improved the accuracy of our system from 0.76 to 0.99.

In order to improve real-time performance of gesture recognition by micro-Doppler map of mmWave Radar, the point cloud based gesture recognition for mmWave Radar is proposed in this paper.Two steps are carried out for mmWave Radar based gesture recognition. The first step is to estimate the point cloud of the gestures by 3D-FFT and the peak grouping. The second step is to train the TRANS-CNN model by combining the multi-head self-attention and the 1D-convolutional network, so as to extract the features in the point cloud data at a deeper level to categorize the gestures. In the experiments, TI mmWave Radar sensor IWR1642 is used as benchmark to evaluate the feasibility of the proposed approach. The results show that the accuracy of the gesture recognition reaches 98.5%. In order to prove the effectiveness of our approach, a simply 2Tx2Rx Radar sensor is developed in our lab and the accuracy of recognition reaches 97.1%. The results show that our proposed gesture recognition approach achieves the best performance in real-time with limited training data, in comparison with the existing methods.

Diabetic retinopathy (DR), a major complication of prolonged diabetes, poses a significant risk of vision loss. Early detection is critical for effective treatment, yet traditional diagnostic methods by ophthalmologists are time-consuming, costly, and subject to variability. This study introduces a novel approach employing a hybrid Convolutional Neural Network-Radial Basis Function (CNN-RBF) classifier integrated with Multi-Scale Discriminative Robust Local Binary Pattern (MS-DRLBP) features for enhanced DR detection. We implemented advanced image preprocessing techniques, including noise reduction, morphological operations, and Otsu’s thresholding, to optimize blood vessel segmentation from retinal images. Our method demonstrates exceptional performance in screening DR, achieving an average of 96.10% precision, 95.35% sensitivity, 97.06% specificity, and 96.10% accuracy. These results significantly outperform traditional methods and offer a promising tool for remote and efficient screening of DR. Applied to publicly available datasets, this research contributes to the development of accessible, accurate diagnostic methods in ophthalmology, potentially reducing the global burden of diabetic vision loss.

Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges such as low imaging quality and high variability. There is a critical need to develop advanced automatic US image analysis methods to enhance diagnostic accuracy and objectivity. Vision transformer, a recent innovation in machine learning, has demonstrated significant potential in various research fields, including general image analysis and computer vision, due to its capacity to process large datasets and learn complex patterns. Its suitability for automatic US image analysis tasks, such as classification, detection, and segmentation, has been recognized. This review provides an introduction to vision transformer and discusses its applications in specific US image analysis tasks, while also addressing the open challenges and potential future trends in its application in medical US image analysis. Vision transformer has shown promise in enhancing the accuracy and efficiency of ultrasound image analysis and is expected to play an increasingly important role in the diagnosis and treatment of medical conditions using ultrasound imaging as technology progresses.

Chinese calligraphy, revered globally for its therapeutic and mindfulness benefits, encompasses styles such as Regular (Kai Shu), Running (Xing Shu), Official (Li Shu), and Cursive (Cao Shu) scripts. Beginners often start with Regular script, advancing to more intricate styles like Cursive. Each style, marked by unique historical calligraphers' contributions, requires learners to discern distinct nuances. The integration of AI in calligraphy analysis, collection, recognition, and classification are pivotal. This study introduces an innovative Convolutional Neural Network (CNN) architecture, pioneering the application of CNN in the classification of Chinese calligraphy. Focusing on the four principal calligraphers' styles from the Tang dynasty (690-907 A.D), this research spotlights the era when the traditional regular script font (Kai Shu) was refined. A comprehensive dataset of 8282 samples from these calligraphers, representing the zenith of regular style, was compiled for CNN training and testing. The model distinguishes personal styles for classification, showing superior performance over existing networks. Achieving 89.5-96.2% accuracy in calligraphy classification, our approach underscores the significance of CNN in both font and artistic style categorization. This research paves the way for advanced studies in Chinese calligraphy and its cultural implications.

Photoelectric smoke detectors are the most cost-effective devices for very early fire alarms. However, due to different light intensity response values for different fire smoke and interference from interferential aerosols, they have a high false alarm rate, which limits their popularity in Chinese homes. To address these issues, an embedded spatial-temporal convolutional neural network (EST-CNN) model is proposed for real fire smokes identification and aerosols (fire smokes and interferential aerosol) classification. EST-CNN consists of three modules including information fusion, scattering feature extraction, and aerosol classification. Moreover, a two dimensional spatial-temporal scattering (2D-TS) matrix is designed to fuse the scattered light intensities in different channels and adjacent time slices, which is the output of the information fusion module and the input of the scattering feature extraction module. EST-CNN is trained and tested with experimental data measured on the established fire test platform using the developed dual-wavelength dual-angle photoelectric smoke detector. The optimal network parameters are selected through extensive experiments resulting in an average classification accuracy of 95.6% for different aerosols with only 66 kB network parameters. The experimental results demonstrate the feasibility of the designed EST-CNN model to be directly installed in existing commercial photoelectric smoke detectors to realize aerosol classification.

More and more people quantify their sleep using wearables and are getting obsessed in their pursuit of optimal sleep (“orthosomnia”). However, it is criticized that many of these wearables are giving inaccurate feedback and even can lead to negative daytime consequences. Acknowledging these facts, we here aim to extend previous findings [] in a new sample of 136 self-reported poor sleepers by implementing optimization procedures to minimize erroneous classification when ambulatory sensing sleep. Firstly, here, we introduce an advanced interbeat-interval (IBI) quality control using a random forest method to account for wearable recordings in naturalistic and more noisy settings. We further aim to improve sleep classification by opting for a loss function model instead of overall epoch-by-epoch accuracy to avoid model biases towards the majority class (i.e., “light sleep”). Using these implementations, we compare the classification performance between the optimized (loss function model) and the accuracy model. We use signals derived from PSG, one-channel ECG, and two consumer wearables: the ECG breast belt Polar® H10 (H10) and the Polar® Verity Sense (VS), an optical Photoplethysmography (PPG) heart-rate sensor. Results reveal high overall accuracy for the new model for ECG (86.3 %, κ=.79), H10 (84.4%, κ=.76), and VS (84.2%, κ=.75) with intended improvements in deep sleep and wake. In addition, the new optimized model displays moderate to high correlations and agreement with PSG on primary sleep parameters, while measures of reliability, expressed in intra-class correlations, suggest excellent reliability for most sleep parameters. Finally, it is demonstrated that the new model is still classifying sleep accurately in 4-classes in users taking heart-affecting and/or psychoactive medication which can be considered a prerequisite for use also in high age groups and/or with common disorders. Further improving and validating sleep stage classification algorithms with affordable wearables may resolve existing scepticism and open the door for such approaches in clinical practice.

Some recent studies show that filters in convolutional neural networks (CNNs) have low color selectivity in datasets of natural scenes such as Imagenet. CNNs, bio-inspired in the visual cortex, are characterized by their hierarchical learning structure, which appears to gradually transform the representation space. Inspired by the direct connection between the LGN and V4, which allows V4 to handle low-level information closer to the trichromatic input in addition to processed information that comes from V2/V3, we propose the addition of a long skip connection (LSC) between the first and last blocks of the feature extraction stage to allow deeper parts of the network to receive information from shallower layers. This type of connection improves classification accuracy by combining simple-visual and complex-abstract features to create more color-selective ones. We have applied this strategy to classic CNN architectures and quantitatively and qualitatively analyzed the improvement in accuracy while focusing on color selectivity. The results show that, in general, skip connections improve accuracy, but LSC improves it even more and enhances the color selectivity of the original CNN architectures. As a side result, we propose a new color representation procedure for organizing and filtering feature maps, making their visualization more manageable.

Object recognition is an essential element of machine intelligence tasks. However, one model cannot practically be trained to identify all the possible objects it encounters. An ensemble of models may be needed to cater to a broader range of objects. Building a mathematical understanding of the relationship between various objects that share comparable outlined features is envisaged as an effective method of improving the model ensemble through a pre-processing stage, where these objects' features are grouped under a broader classification umbrella. This paper proposes a mechanism to train an ensemble of recognition models coupled with a model selection scheme to scale-up object recognition in a multi-model system. An algorithmic relationship between the learnt parameters of a trained classification model and the features of input images is presented in the paper for the system to learn the model selection scheme. The multiple models are built with a CNN structure, whereas the image features are extracted using a CNN/VGG16 architecture. Based on the models' excitation weights, a neural network model selection algorithm, which links a new object with the models and decides how close the features of the object are to the trained models for selecting a particular model for object recognition is developed and tested on a five-model neural network platform. The experiment results show the proposed model selection scheme is highly effective and accurate in selecting an appropriate model for a network of multiple models.

Functional connectivity (FC) is a potential candidate that can increase the performance of brain-computer interfaces (BCIs) in the elderly because of its compensatory role in neural circuits. However, it is difficult to decode FC by current machine learning techniques because of a lack of its physiological understanding. To investigate the suitability of FC in BCI for the elderly, we propose the decoding of lower- and higher-order FCs using a convolutional neural network (CNN) in six cognitive-motor tasks. The layer-wise relevance propagation (LRP) method describes how age-related changes in FCs impact BCI applications for the elderly compared to younger adults. Seventeen younger (24.5±2.7 years) and twelve older (72.5±3.2 years) adults were recruited to perform tasks related to hand-force control with or without mental calculation. CNN yielded a six-class classification accuracy of 75.3% in the elderly, exceeding the 70.7% accuracy for the younger adults. In the elderly, the proposed method increases the classification accuracy by 88.3% compared to the filter-bank common spatial pattern (FBCSP). LRP results revealed that both lower- and higher-order FCs were dominantly overactivated in the prefrontal lobe depending on task type. These findings suggest a promising application of multi-order FC with deep learning on BCI systems for the elderly.

Timely detection of surface damages on wind turbine blades is imperative for minimising downtime and avoiding possible catastrophic structural failures. With recent advances in drone technology, a large number of high-resolution images of wind turbines are routinely acquired and subsequently analysed by experts to identify imminent damages. Automated analysis of these inspection images with the help of machine learning algorithms can reduce the inspection cost, thereby reducing the overall maintenance cost arising from the manual labour involved. In this work, we develop a deep learning based automated damage suggestion system for subsequent analysis of drone inspection images. Experimental results demonstrate that the proposed approach could achieve almost human level precision in terms of suggested damage location and types on wind turbine blades. We further demonstrate that for relatively small training sets advanced data augmentation during deep learning training can better generalise the trained model providing a significant gain in precision.

Detailed built-up area information is valuable for mapping complex urban environments. Although a large number of classification algorithms about built-up areas have been developed, they are rarely tested from the perspective of feature engineering and feature learning. Therefore we launched a unique investigation to provide a full test of the OLI imagery for 15-m resolution built-up area classification in 2015, in Beijing, China. Training a classifier requires many sample points, and we propose a method based on the ESA's 38-meter global built-up area data of 2014, Open Street Map and MOD13Q1-NDVI to achieve rapid and automatic generation of a large number of sample points. Our aim is to examine the influence of a single pixel and image patch under traditional feature engineering and modern feature learning strategies. In feature engineering, we consider spectra, shape and texture as the input features, and SVM, random forest (RF) and AdaBoost as the classification algorithms. In feature learning, the convolution neural network (CNN) is used as the classification algorithm. In total, 26 built-up land cover maps were produced. Experimental results show that: (1) the approaches based on feature learning are generally better than those based on feature engineering in terms of classification accuracy, and the performance of ensemble classifiers e.g., RF, is comparable to that of CNN. Two dimensional CNN and the 7 neighborhood RF have the highest classification accuracy of nearly 91%. (2) Overall, the classification effect and accuracy based on image patches are better than those based on single pixels. The features that can highlight the information of the target category (for example, PanTex and EMBI) can help improve classification accuracy.

The sustainability of the planet and its inhabitants is in dire danger and is among the highest priorities on global agendas such as the Sustainable Development Goals (SDGs) of the United Nations (UN). Solar energy -- among other clean, renewable, and sustainable energies -- is seen as essential for environmental, social, and economic sustainability. Predicting solar energy accurately is critical to increasing reliability and stability, and reducing the risks and costs of the energy systems and markets. Researchers have come a long way in developing cutting-edge solar energy forecasting methods. However, these methods are far from optimal in terms of their accuracies, generalizability, benchmarking, and other requirements. Particularly, no single method performs well across all climates and weathers due to the large variations in meteorological data. This paper proposes SENERGY (an acronym for Sustainable Energy), a novel deep learning-based auto-selective approach and tool that, instead of generalising a specific model for all climates, predicts the best performing deep learning model for GHI forecasting in terms of forecasting error. The approach is based on carefully devised deep learning methods and feature sets through an extensive analysis of deep learning forecasting and classification methods using ten meteorological datasets from three continents. We analyse the tool in great detail through a range of metrics and methods for performance analysis, visualization, and comparison of solar forecasting methods. SENERGY outperforms existing methods in all performance metrics including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Forecast Skills (FS), Relative Forecasting Error, and the normalised versions of these metrics. The proposed auto-selective approach can be extended to other research problems such as wind energy forecasting and predict forecasting models based on different criteria (in addition to the minimum forecasting error used in this paper) such as the energy required or speed of model execution, different input features, different optimisations of the same models, or other user preferences.

IMPORTANCE: On December 10, 2021, the FDA published a Determination Letter, along with a Statistical Review and Evaluation Report, and concluded that under the non-informative prior, the local Bayesian optimal interval design (BOIN) design, in its revised form, can be designated fit-for-purpose for identifying the maximum tolerated dose of a new drug, assuming that dose-toxicity relationship is monotonically increasing. Although setting the BOIN design parameter p.tox = 1.4 * target.DLT.rate is recommended in almost all BOIN methodology articles and is the default value in the R package BOIN, it's unclear if the choice of p.tox should only depend on the target DLT rate and if certain range of p.tox could produce the same BOIN boundary table. DESIGN: In this simulation study, following parameters were varied one at a time, using R package BOIN, to explore their effects on the equivalence intervals of p.saf and p.tox: 1) target DLT rate, 2) n.earlystop, 3) cutoff.eli, 4) cohortsize, and 5) ncohort. And a simple 3+3 design was used as an example to explore equivalent sets of BOIN design parameters that can generate the same boundary table. RESULTS: When the early stopping parameter n.earlystop is relatively small or the cohortsize value is not optimized via simulation, it might be better to use p.tox < 1.4 * target.DLT.rate, or try out different cohort sizes, or increase n.earlystop, whichever is both feasible and provides better operating characteristics. This is because if the cohortsize was not optimized via simulation, even when n.earlystop = 12 and cohortsize > 3, the BOIN escalation/de-escalation rules generated using p.tox = 1.4 * target.DLT.rate could be exactly the same as those calculated using p.tox > 3 * target.DLT.rate, which might not be acceptable for some pediatric trials targeting 10% DLT rate. The traditional 3+3 design stops the dose finding process when 3 patients have been treated at the current dose level, 0 DLT has been observed, and the next higher dose has already been eliminated. If additional 3 patients were required to be treated at the current dose in the situation described above, the decision rules of this commonly used 3+3 design could be generated using BOIN design with target DLT rates ranging from 18% to 29%, p.saf ranging from 8% to 26%, and different p.tox values ranging from 39% to 99%. These BOIN parameters also need to satisfy a set of conditions. Meaning: This study demonstrates the importance of interpreting BOIN design parameter p.tox as an interval of toxicity rates that are considered too toxic, rather than one prespecified value that corresponds to the lowest toxicity probability that is deemed overly toxic. When designing a dose-finding trial using BOIN, it is important to perform simulation studies to identify equivalent sets of BOIN design parameters that can generate the same boundary table so that we can better compare the safety properties of different boundary tables.

The focus of the current research indicates a new Bianchi type-V anisotropic, homogeneous astrophysical model with modified theory of f(R, T) gravity and Λ(t), time-dependent cosmological constant. The significant effect of the model is that the field equations solutions find using a time-dependent quadratic deceleration parameter. We observed anisotropy parameter remains constant both in the belated universe and early universe. The deportment of the equation of state (EOS) parameter, pressure, and energy density, cosmological constant and other parameters are also discussed. This cosmological model indicated the possibility of an accelerating universe with negative pressure, such as a universe dominated by dark energy. Om(z) diagnostic test suggested that the universe starts with quintessence nature and ends as a phantom model. Also, energy conditions of this model are represented here to ensure the model is physically reasonable and based on observations.

This paper presents the symmetries of differential equations associated with one-variable and Bivariate Hermite polynomials by proposing a representation of Lie algebra for these differential operators. Applying the Baker-Campbell-Hausdorff formula to these algebras, results in new relations and generating functions in one-variable and Bivariate Hermite polynomials. A general form of representation for other orthogonal polynomials such as Laguerre polynomials is introduced.

The commitment of the EU to Corporate Social Responsibility (CSR) is projected in the EU law about annual reporting by businesses. Since EU member states further develop this framework by their own domestic laws, annual reporting with CSR information is not unified and just partially mandatory in the EU. Do all European businesses report CSR information and what public declaration to society do they provide with it? The main dual purpose of this paper is identifying the parameters of this annual reporting duty and studying the CSR information provided by the ten largest Czech companies in their annual statements for 2013-2017. Based on legislative research and the teleological interpretation, the current EU legislative framework with Czech particularities is presented and, via a case study exploring 50 annual reports, the data about the type, extent and depth of the CSR is dynamically and comparatively assessed. It appears that, at a minimum, large Czech businesses satisfy their legal duty and e-report on CSR in a similar extent, but in dramatically different quality. Employee matters and adherence to international standards are used as a public declaration to society more than the data on environmental protection, while social matters and R&D are played down.

MIMO (multiple-input multiple-output) radar provides much more flexibility than the traditional radar for its ability to realize far more observation channels than the actual number of T/R (transmit and receive) elements. Designing the array of MIMO imaging radar, the commonly used virtual array theory generally assumes that all elements are placed on the same line. However, due to the physical size of the antennas and coupling effect between T/R elements, a certain height difference between T/R arrays is essential, resulting in the defocusing of edge points of the scene. On the other hand, the virtual array theory implies far-field approximation, leading to inevitable high grating lobes in the imaging result of near-field edge points of the scene observed by common MIMO array. To tackle these problems, this paper derives the relationship between target’s PSF (point spread function) and pattern of T/R arrays, by which the design criterion of near-field imaging MIMO array is presented. Firstly, the proper height between T/R arrays is designed to focus the near-field edge points well. Secondly, the far-field array is modified to suppress the grating lobes in the near-field area. Finally, the validity of the proposed methods is verified by simulations and an experiment.

Machine learning (ML) is enabling augmented reality (AR) to gain popularity in various fields, including gaming, entertainment, healthcare, and education. ML enhances AR applications in education by providing accurate visualizations of objects. For AR systems, ML algorithms facilitate the recognition of objects and gestures from kindergarten through university. The purpose of this survey is to provide an overview of various ways in which ML techniques can be applied within the field of AR within education. The first step is to describe the background of AR. In the next step, we will discuss the ML models that are used in AR education applications. Additionally, we discuss how ML is used in AR. Each subgroup’s challenges and solutions can be identified by analyzing these frameworks. In addition, we outline several research gaps and future research directions in ML-based AR frameworks for education.

It is important for food recognition to separate each ingredient within a food image at the pixel level. In this paper, we propose a new approach to segment ingredients by utilizing a CNN-based Single-Ingredient Classification Model. In detail, we firstly introduce a standardized biological-based hierarchical ingredient structure and construct a single-ingredient image dataset based on this structure. Then, we build a single-ingredient classification model based on a novel convolutional neural network (CNN) architecture that utilizes an attention mechanism. Afterwards, we propose a new framework for segmentation using the above single-ingredient classification model as the backbone. In this framework, two methods are involved in segmenting ingredients in the food images. We introduce five evaluation metrics (IoU, Dice, Purity, Entirety, Loss of GTs) to assess the performance of ingredient segmentation in terms of ingredient classification. Extensive experiments demonstrate the effectiveness of the proposed method, achieving an maximal mIoU of 0.65, mDice of 0.77, mPurity of 0.83, mEntirety of 0.80, and mLoGTs of 0.06 on the FoodSeg103 dataset. The results confirm that our CNN-based architecture achieves higher segmentation performance compared to ResNet18 and EfficientNet-B0 when used as the backbone for ingredient segmentation. We believe that our ingredient segmentation approach lays the foundation for subsequent ingredient recognition.

Hyperspectral image and LiDAR image fusion plays a crucial role in remote sensing by capturing spatial relationships and modeling semantic information for accurate classification and recognition. However, existing methods, like Graph Convolutional Networks (GCNs), face challenges in constructing effective graph structures due to variations in local semantic information and limited receptiveness to large-scale contextual structures. To overcome these limitations, we proposed a invariant attribute-driven binary bi-branch classification (IABC) method which is a unified network that combines binary Convolutional Neural Network (CNN) and GCN with invariant attributes. Our approach utilizes a joint detection framework that can simultaneously learn features from small-scale regular regions and large-scale irregular regions, resulting in an enhanced structured representation of HSI and LiDAR images in the spectral-spatial domain. This approach not only improves the accuracy of classification and recognition but also reduces storage requirements and enables real-time decision-making, which is crucial for effectively processing large-scale remote sensing data. Extensive experiments demonstrates the superior performance of our proposed method in hyperspectral image analysis tasks. The combination of CNNs and GCNs allows for accurate modeling of spatial relationships and effective construction of graph structures. Furthermore, the integration of binary quantization enhances computational efficiency, enabling real-time processing of large-scale data. Therefore, our approach presents a promising opportunity for advancing remote sensing applications using deep learning techniques.

Reducing the costs of repairing concrete structures damaged due to the appearance of cracks and reducing the number of people involved in the process of their repair is the subject of a multitude of experimental studies. Special emphasis should be placed on research involving industrial by-products, the disposal of which has a negative environmental impact, as is the case in the research presented in this paper. The basic idea was to prepare a mortar with added granulated blast furnace slag from Smederevo Steel Mill and then treat artificialy produced cracks with a Sporosarcina pasteurii DSM 33 suspension under the conditions of sterile demineralized and water from Danube river in order to simulate natural conditions. The results show a bio-stimulated healing efficiency of 32.02% in sterile demineralized water and 42.74% in Danube water already after 14 days. The SEM images clearly show calcium carbonate crystals as the main compound that has started to fill the crack, and the crystals are much more developed under the Danube water conditions. As a special type of research, microscopic images of cracks were classified into those with and without the presence of bacterial culture. By applying convolutional neural networks (ResNet 50), the classification success rate was 91.55%.

The continuously developing project aims to build an informatics system enabling analysis of spatial and temporal parameters of movement activities occurring in the sport of speed climbing. The monitoring system (climbing information speed system – CISS) is to be used for conducting comprehensive scientific research in the field of speed climbing. The system enables the evaluation of the training process of climbers at various levels of competition. The study analysis was based on video. The video recording with a camera positioned at a short distance (10 m) from the wall. The marker was positioned closest to the centre of mass (gravity) BMC. Results: development of a system for data collection and analysis of the climbing run based on video recording (application of the Kanade-Lucas-Tomasi (KLT) algorithm). Our results showed that used devices can measure a wide range of specific internal and external variables during speed climbing. Some of the analyzed parameters were significantly correlated with speed climbing time. These results could be a theoretical basis for future research and for training program’s preparation.

The interpretation of land use and land cover (LULC) is an important issue in the fields of high-resolution remote sensing (RS) image processing and land resource management. Fully training a new or existing convolutional neural network (CNN) architecture for LULC classification requires a large amount of remote sensing images. Thus, fine-tuning a pre-trained CNN for LULC detection is required. To improve the classification accuracy for high resolution remote sensing images, it is necessary to use another feature descriptor and to adopt a classifier for post-processing. A fully connected conditional random fields (FC-CRF), to use the fine-tuned CNN layers, spectral features, and fully connected pairwise potentials, is proposed for image classification of high-resolution remote sensing images. First, an existing CNN model is adopted, and the parameters of CNN are fine-tuned by training datasets. Then, the probabilities of image pixels belong to each class type are calculated. Second, we consider the spectral features and digital surface model (DSM) and combined with a support vector machine (SVM) classifier, the probabilities belong to each LULC class type are determined. Combined with the probabilities achieved by the fine-tuned CNN, new feature descriptors are built. Finally, FC-CRF are introduced to produce the classification results, whereas the unary potentials are achieved by the new feature descriptors and SVM classifier, and the pairwise potentials are achieved by the three-band RS imagery and DSM. Experimental results show that the proposed classification scheme achieves good performance when the total accuracy is about 85%.

This article examines the diagnosis of the Agricultural Innovation System (SIA) in the department of Tolima, Colombia, as part of a project led by the Colombian Ministry of Agriculture and Rural Development and the Technological University of Pereira (TUP), which also evaluated the National Agricultural Innovation System (NAIS) in regions such as Chocó, Bolívar, and Meta. A methodology was used that involved a survey with 58 questions on a Likert scale to 300 participants, evaluated with congruence and relevance indexes, identifying key variables in the operation of the Agricultural Innovation System (AIS). A survey was also applied to actors of the National Innovation System for Higher Education in Agriculture, A survey was also applied to map the participating actors in the regional agricultural innovation systems of Tolima to identify gaps in extension, innovation, development, sustainability, ICT, education and training. Among the conclusions, it stands out that the associativity subsystem presents the lowest lag and is close to a score of two on the scale of gaps, evaluation carried out among the five subsystems including extension, ICT, environmental aspects, and pub-lic policy. The department of Tolima shows low performance in innovation and ICT, while the extension is less lagging. In Chaparral there is a general lag, with innovation being the worst evaluated subsystem. Rovira obtains high scores in most subsystems, although innovation and ICT have lower scores. At the national and regional levels, innovation is low, and articulation among NARS actors is insufficient, which highlights the need to promote good practices, strategies, and projects.

Free-space communication is a leading component in global communications. Its advantages relate to a broader signal spread, no wiring, and ease of engagement. Satellite communication services became recently attractive to mega-companies that foresee an excellent opportunity to connect disconnected remote regions, serve emerging machine-to-machine communication, Internet-of-things connectivity, and more. Satellite communication links suffer from arbitrary weather phenomena such as clouds, rain, snow, fog, and dust. In addition, when signals approach the ground station, it has to overcome buildings blocking the direct access to the ground station. Therefore, satellites commonly use redundant signal strength to ensure constant and continuous signal transmission, resulting in excess energy consumption, challenging the limited power capacity generated by solar energy or the fixed amount of fuel. This research proposes LTSM, an artificial recurrent neural network technology that provides a time-dependent prediction of the expected attenuation level due to rain and fog and the signal strength that remained after crossing physical obstacles surrounding the ground station. The satellite transmitter is calibrated accordingly. The satellite outgoing signal strength is based on the predicted signal strength to ensure it will remain strong enough for the ground station to process it. The instant calibration eliminates the excess use of energy resulting in energy savings.

(1) Background: AI technology has been deeply applied to online shopping platform to provide more accurate and personalized services for consumers. It is of great significance to study the different functional experience of AI for consumers to improve the current application status of AI technology.(2)Method: Based on the "S-O-R" model, this study divided the AI technology expe-rienced by the consumers of online shopping platform into accuracy, insight and interaction experience. Takes the perceived value as the mediating variable from the prospect of perceived utility value and perceived hedonic value. This article use empirical research method to analyze the effect of three dimensions of online shopping AI experience to research the internal influence mechanism of consumers purchase intention. (3) Results:① The accuracy, insight and interaction experience of AI marketing technology have a significant positive impact on consumers' per-ceived utility value and hedonic value respectively; ②Both of the perceived utility value and perceived hedonic value obtained by AI technology experience can promote the formation of consumers' purchase intention; ③ The perceived hedonic value was better than perceived utility value to promote the consumers' purchase intention; ④The results of multi group analysis show that some younger and less experiences consumers groups prefer the pleasure experience such as shopping desire stimulation, shopping process relaxation and pleasure that AI marketing brought. However, utilitarian value cannot promote this kind of consumers' purchase intention. (4) Con-clusions: Perceived utility value and perceived hedonic value can be the intermediary between AI technology and consumers' purchase intention.

Deep Neural Network (DNN) inference demands substantial computing power, resulting in significant energy consumption. A large number of negative output activations in convolution layers are rendered zero due to the invocation of the ReLU activation function. This results in a substantial number of unnecessary computations that consume significant amounts of energy. This paper presents ECHO: Energy-efficient Computation Harnessing Onilne Arithmetic - A MSDF-based accelerator for DNN inference, designed for computation pruning, utilizing an unconventional arithmetic paradigm known as online/ most-significant digit first (MSDF) arithmetic which performs computations in a digit-serial manner. The MSDF digital serial computation of online arithmetic enables overlapped computation of successive operations leading to substantial performance improvements. The online arithmetic, coupled with a negative output detection scheme, facilitates early and precise recognition of negative outputs. This, in turn, allows for the timely termination of unnecessary computations, resulting in a reduction of energy consumption. The implemented design has been realized on the Xilinx Virtex-7 VU3P FPGA and subjected to a comprehensive evaluation through a rigorous comparative analysis involving widely used performance metrics. Experimental results demonstrate promising power and throughput improvements compared to contemporary methods. In particular, the proposed design achieved an average improvement in power consumption of up to 81%, 82.9%, and 40.6% for VGG-16, ResNet-18, and ResNet-50 workloads compared to the conventional bit-serial design, respectively. Furthermore, significant average speedups of 2.39×, 2.6×, and 2.42 were observed when comparing the proposed design to conventional bit-serial designs for VGG-16, ResNet-18, and ResNet-50 models respectively.

The main source of electricity worldwide stems from fossil fuels, contributing to air pollution, global warming, and associated adverse effects. This study explores wind energy as a potential alternative. Nevertheless, the variable nature of wind introduces uncertainty in its reliability. Thus, it is necessary to identify an appropriate machine learning model capable of reliably forecasting wind speed under various environmental conditions. This research compares the effectiveness of artificial neural networks (ANN) and convolutional neural networks (CNN) in predicting wind speed across three locations in South Africa, characterised by different weather patterns. Empirical results show that CNN outperforms ANN in accurately forecasting wind speed under different weather conditions. This superiority is likely due to the inherent architectural attributes of CNNs, including feature extraction capabilities, spatial hierarchy learning, and resilience to spatial variability. These results could be useful to decision-makers in the energy sector.

The utilization of Pig Emotion Recognition (PER) driven by Artificial Intelligence (AI) promises to mitigate labor costs and alleviate stress among domestic pigs, thereby minimizing the need for consistent human intervention. Nevertheless, this research acknowledges the inherent limitations within the raw PER datasets, which often include irrelevant porcine features, hence impeding genuine progress in real-world evaluations. A significant proportion of PER datasets derive from sequential pig imagery obtained from video recordings, and a common pitfall in these studies is the unregulated shuffling of data. This lack of control can result in the overlap of data samples between training and testing groups, thereby yielding skewed experimental evaluations. To address these challenges, this paper introduces a novel solution in the form of the Semi-Shuffle-Pig Detector (SSPD) for PER datasets, with the intent to facilitate a less biased experimental output. By applying the SSPD, we can ensure that all testing data samples remain distinct from the training datasets, and any superfluous information from raw images is systematically discarded. This optimized method enhances the true performance of classification, providing unbiased experimental evaluations. Notably, our approach has led to a remarkable improvement in the Isolation After Feeding (IAF) metric by 20.2\% and achieved higher accuracy in segregating IAF and Paired After Feeding (PAF) classifications exceeding 92\%. This methodology, thereby, ensures the preservation of pertinent data within the PER system and eliminates potential biases in experimental evaluations. Consequently, it elevates the accuracy and reliability of real-world PER applications, resulting in a tangible positive impact on both pig welfare management and food safety standards.

Ultrasonic-guided lamb wave approach is an effective non-destructive testing (NDT) method used for detecting localized mechanical damage, corrosion, and welding defects experienced in metallic pipelines. Signal processing of the guided waves is often challenged due to the complexity of operational conditions and environments in the pipelines. Machine learning approaches in recent years, including convolutional neural networks (CNN) and long short-term memory (LSTM), have exhibited their advantages to overcome these challenges for signal process and data classification of complex systems, thus great potential for damage detection of critical oil/gas pipeline structures. In this study, a CNN-LSTM hybrid model is utilized for decoding ultrasonic guided waves for damage detection of metallic pipelines, and twenty-nine features are extracted as input to classify different types of defects from metallic pipes. The prediction capacity of the CNN-LSTM model is assessed by comparing it to the CNN and LSTM. The results demonstrate that the CNN-LSTM hybrid model exhibits much higher accuracy, with 94.8%, as compared to those of CNN and LSTM. Interestingly, the results also reveal that predetermined features, including time-, frequency-, and time-frequency domains, could significantly improve the robustness of the deep learning approaches, even though the deep learning approaches are often believed they include automated feature extraction, without the hand-crafted steps as the shallow learning do. Furthermore, the CNN-LSTM model displays higher performance when the noise level is relatively low (e.g., SNR=9 or higher), as compared to the other two models, but its prediction drops gradually with the increase of the noise.

The prompt and accurate diagnosis of breast lesions, including the distinction between cancer, non-cancer, and suspicious cancer, plays a crucial role in the prognosis of breast cancer. In this paper, we introduce a novel method based on feature extraction and reduction for detection of breast cancer in mammography images. First, we extract features from multiple pre-trained convolutional neural network (CNN) models, and then concatenate them. The most informative features are selected based on their mutual information with the target variable. Subsequently, the selected features can be classified using a machine learning algorithm. We evaluate our approach using four different machine learning algorithms, and our results demonstrate that the neural network-based classifier yields an accuracy as high as 92% for the RSNA dataset which is a new dataset that provides two views and additional features such as age. We compare our proposed algorithm with state-of-the-art methods and demonstrate its superiority, particularly in terms of accuracy and sensitivity. For the MIAS dataset, we achieve an accuracy as high as 94.5%, and for the DDSM dataset, an accuracy of 96% is attained. These results highlight the effectiveness of our method in accurately diagnosing breast lesions and surpassing existing approaches.

Deepfakes are manipulated or altered images, or video, that are created using deep learning models with high levels of photorealism. The two popular methods of producing a deepfake are based on either convolutional neural networks (CNN), or autoencoders. Deepfakes created using CNN comparatively show higher qualities of realism, yet oftentimes leave artifacts and distortions in the generated media that can be detected using machine learning and deep learning algorithms. In recent years, there has been an influx of periocular image and video data because of the increase usage of face masks. By wearing masks, much of what is used for facial recognition is hidden, leaving only the periocular region visible to an observer. This loss of vital information leads to easier misidentification of media, allowing deepfakes to less likely be identified as fake. In this work, feature extraction methods, such as Scale-Invariant Feature Transform (SIFT), Histogram of Oriented Gradients (HOG), and CNN, are used to train an ensemble deep learning model to detect deepfakes in videos on a frame-by-frame level based on the periocular region. Our proposed model is able to distinguish original and manipulated images with accuracies around 98.9 percent, which is an improvement to previous works by combining SIFT and HOG for deepfake detection in convolutional neural networks.

Advancements in deep learning and availability of medical imaging data have led to use of CNN based architectures in disease diagnostic assisted systems. In spite of the abundant use of reverse transcription-polymerase chain reaction (RT-PCR) based tests in COVID-19 diagnosis, CT images offer an applicable supplement with its high sensitivity rates. Here, we study classification of COVID-19 pneumonia (CP) and non-COVID-19 pneumonia (NCP) in chest CT scans using efficient deep learning methods to be readily implemented by any hospital. We report our deep network framework design that encompasses Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory (biLSTM) architectures. Our study achieved high specificity (CP: 98.3%, NCP: 96.2% Healthy: 89.3%) and high sensitivity (CP: 84.0%, NCP: 93.9% Healthy: 94.9%) in classifying COVID-19 pneumonia, non-COVID-19 pneumonia and healthy patients. Next, we provide visual explanations for the CNN predictions with gradient-weighted class activation mapping (Grad-CAM). The results provided a model explainability by showing that Ground Glass Opacities (GGO), indicators of COVID-19 pneumonia disease, were captured by our CNN network. Finally, we have implemented our approach in three hospitals proving its compatibility and efficiency.

The present paper reports an alternative solution of the measurement problem in quantum theory. The measurement problem can be characterized as that the U-procedure verses the R-procedure. The R-procedure is tested by the Yes/No measurement originally proposed by von Neuman and discussed in details by Penrose. We propose a novel stochastic sampling method to tackle the measurement paradox. Each testing sample produces a pair of Yes-number c and No-number d, which in turn generates a sample phase with respect to the exponential form of (c+id). All the sample phases forms a group G_R. Taking G_R as the sampling potential, combined with the dynamic phase group G_U，we establish a unified model of U-procedure and R-procedure for the evolution of wavefunction. Based on the Born rule, the probability of a sample is given by the squared magnitude of （c+id）. Some metaproperties of the new U-R model, such as natural transformation, consistency, and completeness, are presented. The present work provides a new picture of quantum mechanics and alike. The measurement problem widely exists in dynamic analysis, higher cognition, and large data modeling. Thus, the work reported here has a wide range of applications. Keywords: The measurement problem; U-R procedures; the Yes/No type measurement; stochastic sampling; sample phase; Born probability.

B-cell chronic lymphocytic leukemia (B-CLL) is the most common type of leukemia in the Western world. Mutations in different genes, such as TP53 and ATM, and deletions in specific chromosomal regions, including 11q or 17p, have been associated with a worse prognosis for the disease. Recent research from our group has demonstrated that, contrary to the usual cancer development process through missense mutations, B-CLL is driven by the overexpression of the small GTPase RRAS2 in its wild-type form, without activating mutations. While some mouse models of this disease have been developed to date and are commonly used in B-CLL research, they come with various disadvantages, such as a long waiting period until the leukemia fully develops, the need for cell engraftment, or, in some cases, a failure to replicate the alterations found in human patients. We have recently introduced Rosa26-RRAS2fl/flxmb1-Cre as a new mouse model of B-CLL with full disease penetrance. In this work, we have validated this mouse model as a novel tool for the development of new therapies for B-CLL by testing two of the most widely applied targeted agents: ibrutinib and venetoclax. This also paves the way for the development of new targeted agents against R-RAS2 itself, an approach that has not yet been explored in clinical practice.

The RNA-binding protein Human antigen R (HuR) regulates stability, translation, and nucleus-to-cytoplasm shuttling of its target mRNAs. The protein has been progressively recognized as a relevant therapeutic target for several pathologies like cancer, neurodegeneration, as well as inflammation. Inhibitors of mRNA binding to HuR might thus be beneficial against a variety of diseases. Here we present the rational identification of structurally novel HuR inhibitors. In particular, by combining chemoinformatics approaches, high throughput virtual screening and RNA–protein pull-down assays, we show that the 4-(2-(2,4,6-trioxotetrahydropyrimidin-5(2H)-ylidene)hydrazineyl)benzoate ligand exhibits dose-dependent HuR inhibition in binding experiments. Importantly, the chemical scaffold is new with respect to the so-far known HuR inhibitors, opening up a new avenue for the design of pharmaceutical agents targeting this important protein.

We investigate the innovational determinants of “Patent Applications” in Europe. We use data from the European Innovation Scoreboard-EIS of the European Commission for 36 countries in the period 2010-2019. We use Panel Data with Fixed Effects, Panel Data with Random Effects, Pooled OLS, WLS and Dynamic Panel. We found that the variables that have a deeper positive association with “Patent Applications” are “Human Resources” and “Intellectual Assets”, while the variables that show a more intense negative relation with Patent Applications are “Employment Share in Manufacturing” and “Total Entrepreneurial Activity”. A cluster analysis with the k-Means algorithm optimized with the Silhouette Coefficient has been realized. The results show the presence of two clusters. A network analysis with the distance of Manhattan has been performed and we find three different complex network structures. Finally, a comparison is made among eight machine learning algorithms for the prediction of the future value of the “Patent Applications”. We found that PNN-Probabilistic Neural Network is the best performing algorithm. Using PNN the results show that the mean future value of “Patent Applications” in the estimated countries is expected to decrease of -0.1%.

In this article we have estimated the value of “Opportunity Driven Entrepreneurship” in Europe. We use data from European Innovation Scoreboard-EIS of the European Commission for 36 countries in the period 2010-2019. We use Panel Data with Fixed Effects, Panel Data with Random Effects, WLS, Pooled OLS, and Dynamic Panel. Our results show that “Opportunity Driven Entrepreneurship” is positively associated, among others, to “Innovation Friendly Environment” and “Turnover Share Large Enterprises”, while it is negatively associated, among others, to “Sales Impacts” and “R&D Expenditure Business Sectors”.

In this article we estimate the value of “Non-R&D Innovation Expenditures” in Europe. We use data from the European Innovation Scoreboard-EIS of the European Commission from the period 2010-2019. We test data with the following econometric models i.e.: Pooled OLS, Dynamic Panel, Panel Data with Fixed Effects, Panel Data with Random Effects, WLS. We found that “Non-R&D Innovation Expenditures” is positively associated among others to “Innovation Index” and “Firm Investments” and negatively associated among others to “Human Resources” and “Government Procurement of Advanced Technology Products”. We use the k-Means algorithm with either the Silhouette Coefficient and the Elbow Method in a confrontation with the network analysis optimized with the Distance of Manhattan and we find that the optimal number of clusters is four. Furthermore, we propose a confrontation among eight machine learning algorithms to predict the level of “Non-R&D Innovation Expenditures” either with Original Data-OD either with Augmented Data-AD. We found that Gradient Boost Trees Regression is the best predictor for OD while Tree Ensemble Regression is the best Predictor for AD. Finally, we verify that the prediction with AD is more efficient of that with OD with a reduction in the average value of statistical errors equal to 40,50%.

In this article we investigate the determinants of “New Doctorate Graduates” in Europe. We use data from the EIS-European Innovation Scoreboard of the European Commission for 36 countries in the period 2010-2019 with Pooled OLS, Dynamic Panel, WLS, Panel Data with Fixed Effects and Panel Data with Random Effects. We found that “New Doctorate Graduates” is positively associated, among others, with “Human Resources” and “Government Procurement of Advanced Technology Products” and negatively, associated among others, with “Total Entrepreneurial Activity” and “Innovation Index”. We apply a clusterization with k-Means algorithm either with the Silhouette Coefficient either with the Elbow Method and we found that in both cases the optimal number of clusters is three. Furthermore, we use the Network Analysis with the Distance of Manhattan, and we find the presence of seven network structures. Finally, we propose a confrontation among ten machine learning algorithms to predict the value of “New Doctorate Graduates” either with Original Data-OD either with Augmented Data-AD. Results show that SGD-Stochastic Gradient Descendent is the best predictor for OD while Linear Regression performs better for AD.

In this article we investigate the determinants of the European “Most Cited Publications”. We use data from the European Innovation Scoreboard-EIS of the European Commission for the period 2010-2019. Data are analyzed with Panel Data with Fixed Effects, Panel Data with Random Effects, WLS, and Pooled OLS. Results show that the level of “Most Cited Publications” is positively associated, among others, to “Innovation Index” and “Enterprise Birth” and negatively associated, among others, to “Government Procurement of Advanced Technology Products” and “Human Resources”. Furthermore, we perform a cluster analysis with the k-Means algorithm either with the Silhouette Coefficient and the Elbow Method. We find that the Elbow Method shows better results than the Silhouette Coefficient with a number of clusters equal to 3. In adjunct we perform a network analysis with the Manhattan distance, and we find the presence of 4 complex and 2 simplified network structures. Finally, we present a confrontation among 10 machine learning algorithms to predict the level of “Most Cited Publication” either with Original Data-OD either with Augmented Data-AD. Results show that the best machine learning algorithm to predict the level of “Most Cited Publication” with Original Data-OD is SGD, while Linear Regression is the best machine learning algorithm for the prediction of “Most Cited Publications” with Augmented Data-AD.

In this article we analyze the determinants and the export trend of European countries of medium and high technology products. The data were analyzed using various econometric models, namely WLS, Pooled OLS, Dynamic Panel, Panel Data with Fixed Effects, Panel Data with Random Effects. The results show that exports of medium and high-tech products are positively associated, among other variables, with the value of “Average Annual GDP Growth”, “Total Entrepreneurial Activity” and “Sales Impacts”, and negatively associated with, among other variables, “Human Resources”, “Government and Procurement of Advanced Technology Products” and “Buyer Sophistication”. A cluster analysis was realized with the k-Means algorithm optimized with the Silhouette coefficient. The result showed the presence of only two clusters. Since this result was considered poorly representative of the industrial complexity of the European Union countries, a further analysis was carried out with the Elbow method. The result showed the presence of 6 clusters with the dominance of Germany and the economies connected to the German economy. In addition, a network analysis was carried out using the distance to Manhattan. Four complex network structures and two simplified network structures were detected. A comparison was then made between 10 machine learning algorithms for predicting the value of exports of medium and high-tech products. The result shows that the best performing algorithm is the SGD. An analysis with Augmented Data-AD was implemented with a comparison between 10 machine learning algorithms for prediction and the result shows that the Linear Regression algorithm is the best predictor. The prediction with the Augmented Data-AD allows to reduce the MAE by about 0.0022131 compared to the prediction with the Original Data-OD.

The article affords the question of lifelong learning in Europe using data from the European Innovation Scoreboard-EIS in the period 2010-2019 for 36 countries. The econometric analysis is realized using WLS, Dynamic Panel, Pooled OLS, Panel Data with Fixed Effects and Random Effects. The results show that lifelong learning is, among other variables, positively associated to “Human Resources” and “Government procurement of advanced technology products” and is negatively associated, among others, to “Average annual GDP growth” and “Innovation Index”. A clusterization is realized using the k-Means algorithm with a confrontation between the Elbow Method and the Silhouette Coefficient. Subsequently, a Network Analysis was applied with the distance of Manhattan. The results show the presence of 4 complex and 2 simplified network structures. Finally, a comparison was made among eight machine learning algorithms for the prediction of the value of lifelong learning. The results show that the linear regression is the best predictor algorithm and that the level of lifelong learning is expected to growth on average by 1.12%.